prince-canuma's picture
Upload folder using huggingface_hub (#1)
23272c5 verified
|
raw
history blame
944 Bytes
---
language:
- multilingual
license: mit
tags:
- nlp
- code
- mlx
license_link: https://huggingface.co./microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
inference:
parameters:
temperature: 0.7
widget:
- messages:
- role: user
content: Can you provide ways to eat combinations of bananas and dragonfruits?
---
# mlx-community/Phi-3-medium-128k-instruct-4bit
The Model [mlx-community/Phi-3-medium-128k-instruct-4bit](https://huggingface.co./mlx-community/Phi-3-medium-128k-instruct-4bit) was converted to MLX format from [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co./microsoft/Phi-3-medium-128k-instruct) using mlx-lm version **0.13.1**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Phi-3-medium-128k-instruct-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```